IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v11y2023i7p1566-d1105289.html
   My bibliography  Save this article

Multi-Step Ahead Ex-Ante Forecasting of Air Pollutants Using Machine Learning

Author

Listed:
  • Snezhana Gocheva-Ilieva

    (Faculty of Mathematics and Informatics, Paisii Hilendarski University of Plovdiv, 24 Tzar Asen St, 4000 Plovdiv, Bulgaria)

  • Atanas Ivanov

    (Faculty of Mathematics and Informatics, Paisii Hilendarski University of Plovdiv, 24 Tzar Asen St, 4000 Plovdiv, Bulgaria)

  • Hristina Kulina

    (Faculty of Mathematics and Informatics, Paisii Hilendarski University of Plovdiv, 24 Tzar Asen St, 4000 Plovdiv, Bulgaria)

  • Maya Stoimenova-Minova

    (Faculty of Mathematics and Informatics, Paisii Hilendarski University of Plovdiv, 24 Tzar Asen St, 4000 Plovdiv, Bulgaria)

Abstract

In this study, a novel general multi-step ahead strategy is developed for forecasting time series of air pollutants. The values of the predictors at future moments are gathered from official weather forecast sites as independent ex-ante data. They are updated with new forecasted values every day. Each new sample is used to build- a separate single model that simultaneously predicts future pollution levels. The sought forecasts were estimated by averaging the actual predictions of the single models. The strategy was applied to three pollutants—PM 10 , SO 2 , and NO 2 —in the city of Pernik, Bulgaria. Random forest (RF) and arcing (Arc-x4) machine learning algorithms were applied to the modeling. Although there are many highly changing day-to-day predictors, the proposed averaging strategy shows a promising alternative to single models. In most cases, the root mean squared errors (RMSE) of the averaging models (aRF and aAR) for the last 10 horizons are lower than those of the single models. In particular, for PM 10 , the aRF’s RMSE is 13.1 vs. 13.8 micrograms per cubic meter for the single model; for the NO 2 model, the aRF exhibits 21.5 vs. 23.8; for SO 2, the aAR has 17.3 vs. 17.4; for NO 2 , the aAR’s RMSE is 22.7 vs. 27.5, respectively. Fractional bias is within the same limits of (−0.65, 0.7) for all constructed models.

Suggested Citation

  • Snezhana Gocheva-Ilieva & Atanas Ivanov & Hristina Kulina & Maya Stoimenova-Minova, 2023. "Multi-Step Ahead Ex-Ante Forecasting of Air Pollutants Using Machine Learning," Mathematics, MDPI, vol. 11(7), pages 1-26, March.
    • Handle: RePEc:gam:jmathe:v:11:y:2023:i:7:p:1566-:d:1105289
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/11/7/1566/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2227-7390/11/7/1566/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Daniel Vassallo & Raghavendra Krishnamurthy & Thomas Sherman & Harindra J. S. Fernando, 2020. "Analysis of Random Forest Modeling Strategies for Multi-Step Wind Speed Forecasting," Energies, MDPI, vol. 13(20), pages 1-19, October.
    2. Kang, In-Bong, 2003. "Multi-period forecasting using different models for different horizons: an application to U.S. economic time series data," International Journal of Forecasting, Elsevier, vol. 19(3), pages 387-400.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Snezhana Gocheva-Ilieva & Atanas Ivanov & Hristina Kulina, 2023. "Special Issue “Statistical Data Modeling and Machine Learning with Applications II”," Mathematics, MDPI, vol. 11(12), pages 1-4, June.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Marcellino, Massimiliano & Stock, James H. & Watson, Mark W., 2006. "A comparison of direct and iterated multistep AR methods for forecasting macroeconomic time series," Journal of Econometrics, Elsevier, vol. 135(1-2), pages 499-526.
    2. Hutter, Christian & Weber, Enzo, 2014. "Forecasting with a mismatch-enhanced labor market matching function," IAB-Discussion Paper 201416, Institut für Arbeitsmarkt- und Berufsforschung (IAB), Nürnberg [Institute for Employment Research, Nuremberg, Germany].
    3. Natei Ermias Benti & Mesfin Diro Chaka & Addisu Gezahegn Semie, 2023. "Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects," Sustainability, MDPI, vol. 15(9), pages 1-33, April.
    4. Hitesh Doshi & Kris Jacobs & Rui Liu, 2021. "Information in the Term Structure: A Forecasting Perspective," Management Science, INFORMS, vol. 67(8), pages 5255-5277, August.
    5. Chevillon, Guillaume & Hendry, David F., 2005. "Non-parametric direct multi-step estimation for forecasting economic processes," International Journal of Forecasting, Elsevier, vol. 21(2), pages 201-218.
    6. Guillaume Chevillon, 2007. "Direct Multi‐Step Estimation And Forecasting," Journal of Economic Surveys, Wiley Blackwell, vol. 21(4), pages 746-785, September.
    7. Guanjun Liu & Chao Wang & Hui Qin & Jialong Fu & Qin Shen, 2022. "A Novel Hybrid Machine Learning Model for Wind Speed Probabilistic Forecasting," Energies, MDPI, vol. 15(19), pages 1-16, September.
    8. Chevillon, Guillaume, 2009. "Multi-step forecasting in emerging economies: An investigation of the South African GDP," International Journal of Forecasting, Elsevier, vol. 25(3), pages 602-628, July.
    9. Gong, Yu & Liu, Pan & Zhang, Jun & Liu, Dedi & Zhang, Xiaoqi & Zhang, Xiaojing, 2020. "Considering different streamflow forecast horizons in the quantitative flood risk analysis for a multi-reservoir system," Reliability Engineering and System Safety, Elsevier, vol. 204(C).
    10. Sanchez, Ismael, 2006. "Short-term prediction of wind energy production," International Journal of Forecasting, Elsevier, vol. 22(1), pages 43-56.
    11. Guillaume Chevillon, 2006. "Multi-step Forecasting in Unstable Economies: Robustness Issues in the Presence of Location Shifts," Economics Series Working Papers 257, University of Oxford, Department of Economics.
    12. Christian Hutter & Enzo Weber, 2017. "Mismatch and the Forecasting Performance of Matching Functions," Oxford Bulletin of Economics and Statistics, Department of Economics, University of Oxford, vol. 79(1), pages 101-123, February.
    13. Eliana González Molano & Luis Fernando Melo Velnadia & Anderson Grajales Olarte, 2007. "Pronósticos directos de la inflación colombiana," Borradores de Economia 4246, Banco de la Republica.
    14. Franses, Ph.H.B.F., 2006. "Forecasting 1 to h steps ahead using partial least squares," Econometric Institute Research Papers EI 2006-47, Erasmus University Rotterdam, Erasmus School of Economics (ESE), Econometric Institute.
    15. López, Ana M. & Flores, Mario A. & Sánchez, Juan I., 2017. "Modelos de series temporales aplicados a la predicción del tráfico aeroportuario español de pasajeros: Un enfoque agregado y desagregado/Forecasting of Spanish Passenger Air Traffic Based on Time Seri," Estudios de Economia Aplicada, Estudios de Economia Aplicada, vol. 35, pages 395-418, Mayo.
    16. Eliana González Molano & Luis Fernando Melo Velandia & Anderson Grajales Olarte, 2007. "Pronósticos directos de la inflación colombiana," Borradores de Economia 458, Banco de la Republica de Colombia.
    17. De Gooijer, Jan G. & Hyndman, Rob J., 2006. "25 years of time series forecasting," International Journal of Forecasting, Elsevier, vol. 22(3), pages 443-473.
    18. Jan G. De Gooijer & Rob J. Hyndman, 2005. "25 Years of IIF Time Series Forecasting: A Selective Review," Monash Econometrics and Business Statistics Working Papers 12/05, Monash University, Department of Econometrics and Business Statistics.
    19. Christian Hutter & Enzo Weber, 2015. "Constructing a new leading indicator for unemployment from a survey among German employment agencies," Applied Economics, Taylor & Francis Journals, vol. 47(33), pages 3540-3558, July.
    20. Mohammadipour, Maryam & Boylan, John E., 2012. "Forecast horizon aggregation in integer autoregressive moving average (INARMA) models," Omega, Elsevier, vol. 40(6), pages 703-712.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:11:y:2023:i:7:p:1566-:d:1105289. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.